用小鼠基因数据模拟神经发育，生成可快速学习的微型神经电路。
Structure as Computation: Developmental Generation of Minimal Neural Circuits
- 基于小鼠转录组数据模拟从干细胞到神经元的发育过程。
- 85个成熟神经元形成20万突触网络，训练后MNIST准确率达90%以上。
- 无需修改架构，即可在少量训练下高效完成图像分类任务。
本研究通过小鼠单细胞转录组数据推导的基因调控规则，模拟皮层神经发生的发展过程，从单个干细胞开始。发育过程自发产生5000个细胞的异质群体，但仅生成85个成熟神经元，占总数1.7%。这85个神经元构成一个密集连接的核心网络，包含200,400个突触，平均每神经元有4,715个连接。初始状态下该最小电路在MNIST上表现随机，但经过一次标准训练后，准确率跃升至90%以上（超过80个百分点提升），典型结果在89%-94%之间，取决于发育中的随机性。相同电路未做任何架构修改或数据增强，经一次训练后在CIFAR-10上达到40.53%准确率。结果表明，发育规则能塑造出对快速学习极为有利的通用拓扑结构，暗示生物发育过程天然蕴含强大的结构先验以实现高效计算。
原文摘要 · Abstract (English)
This work simulates the developmental process of cortical neurogenesis, initiating from a single stem cell and governed by gene regulatory rules derived from mouse single-cell transcriptomic data. The developmental process spontaneously generates a heterogeneous population of 5,000 cells, yet yields only 85 mature neurons - merely 1.7% of the total population. These 85 neurons form a densely interconnected core of 200,400 synapses, corresponding to an average degree of 4,715 per neuron. At iteration zero, this minimal circuit performs at chance level on MNIST. However, after a single epoch of standard training, accuracy surges to over 90% - a gain exceeding 80 percentage points - with typical runs falling in the 89-94% range depending on developmental stochasticity. The identical circuit, without any architectural modification or data augmentation, achieves 40.53% on CIFAR-10 after one epoch. These findings demonstrate that developmental rules sculpt a domain-general topological substrate exceptionally amenable to rapid learning, suggesting that biological developmental processes inherently encode powerful structural priors for efficient computation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。